vs

pgvector vs VectorChord

pgvector: The standard Postgres extension for vector similarity search with HNSW and IVFFlat indexes. VectorChord: Disk-friendly Postgres vector extension using IVF + RaBitQ, the successor to pgvecto.rs.

key differences

  • Licensing: pgvector is open source (permissive) (PostgreSQL License); VectorChord is open source (copyleft) (AGPL-3.0 or Elastic License 2.0 (dual)).
  • VectorChord is built for larger datasets (≤ 1 PB) than pgvector (≤ 10 TB).
  • Horizontal scaling is addon in pgvector and none in VectorChord.

choose pgvector for

  • +Adding semantic search to an existing Postgres app
  • +RAG with permission filtering via SQL joins
  • +Recommendations next to product data
  • +Deduplication and similarity lookups

best at · Vector search, RAG, OLTP

choose vectorchord for

  • +Scaling Postgres vector search past pgvector's comfort zone
  • +Cost-efficient disk-based RAG retrieval
  • +Hybrid BM25 plus vector search in Postgres

best at · Vector search, RAG, OLTP

overview
Primary model
Vector
Vector
Also supports
Relational
Relational
Type
Extension
Extension
Status
Active
Active
Developer
Andrew Kane and pgvector contributors
TensorChord Inc.
First release
2021
2024
Latest version
0.8.7 (Oct 1, 2026)
1.1.1 (Feb 28, 2026)
License
Open source (permissive)PostgreSQL License
Open source (copyleft)AGPL-3.0 or Elastic License 2.0 (dual)
Free tier
✓
✓
popularity
WhichDB Score
40.0
13.7
Rank
#44
#250
GitHub stars
23.5K
1.8K
Stack Overflow questions
91
–
scale & guarantees
Comfortable data size
Medium (≤ 10 TB)
Large (≤ 1 PB)
Horizontal scaling
Addon
None
Multi-region
Read replicas
Read replicas
ACID
Full
Full
Consistency
Strong
Strong
Schema
Strict
Strict
Architecture
Single node, Primary replica, Client server
Single node, Primary replica, Client server
deployment
Self-hosted
✓
✓
Vendor-managed cloud
—
✓
Serverless
—
—
Embedded
—
—
Edge
—
—
Clouds
AWS, Google Cloud, Azure, DigitalOcean, Heroku, Render
–
capabilities
Transactions
✓
✓
Joins
✓
✓
Secondary indexes
✓
✓
Full-text search
✓
✓
Vector search
✓
✓
Geospatial
—
—
JSON
✓
✓
Change data capture
✓
✓
Triggers
✓
✓
Stored procedures
✓
✓
Materialized views
✓
✓
TTL / expiry
—
—
Pub/Sub
✓
✓
Columnar storage
—
—
In-memory
—
—
Durable persistence
✓
✓
Compression
✓
✓
Encryption at rest
—
—
Role-based access
✓
✓
Time travel
—
—
Branching
—
—
Online schema changes
✓
✓
Streaming ingest
—
—
Offline sync
—
—
Runs in WebAssembly
—
—
interfaces
Query languages
SQL
SQL
Client languages
Python, JavaScript, Go, Java, Ruby, Rust, C#, PHP
Any PostgreSQL driver
Best for
Vector search, RAG, OLTP
Vector search, RAG, OLTP

pgvector vs VectorChord: FAQ

What is the difference between pgvector and VectorChord?

pgvector: The standard Postgres extension for vector similarity search with HNSW and IVFFlat indexes. VectorChord: Disk-friendly Postgres vector extension using IVF + RaBitQ, the successor to pgvecto.rs. Licensing: pgvector is open source (permissive) (PostgreSQL License); VectorChord is open source (copyleft) (AGPL-3.0 or Elastic License 2.0 (dual)). VectorChord is built for larger datasets (≤ 1 PB) than pgvector (≤ 10 TB). Horizontal scaling is addon in pgvector and none in VectorChord.

When should I choose pgvector over VectorChord?

Choose pgvector for adding semantic search to an existing Postgres app, RAG with permission filtering via SQL joins and recommendations next to product data. Choose VectorChord for scaling Postgres vector search past pgvector's comfort zone, cost-efficient disk-based RAG retrieval and hybrid BM25 plus vector search in Postgres.

Is pgvector or VectorChord more popular?

pgvector ranks #44 on the WhichDB Score (40.0/100) and VectorChord ranks #250 (13.7/100). Popularity is not fit: check the requirements that matter for your project.

Are pgvector and VectorChord open source?

Yes. pgvector is open source. License: PostgreSQL License. Yes. VectorChord is open source. License: AGPL-3.0 or Elastic License 2.0 (dual).